Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 307 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.7294. Min Range: -1.7294

Max Act: 1.7294. Min Act: -0.0001

Data Index: 1464120 (Python Code)

Max Activating Token Index: 124

Text #1

Max Range: 1.7294. Min Range: -1.7294

Max Act: 1.4433. Min Act: -0.0001

Data Index: 1587538 (Python Code)

Max Activating Token Index: 377

Text #2

Max Range: 1.7294. Min Range: -1.7294

Max Act: 1.4649. Min Act: -0.0001

Data Index: 1635458 (Python Code)

Max Activating Token Index: 683

Text #3

Max Range: 1.7294. Min Range: -1.7294

Max Act: 1.4463. Min Act: -0.0001

Data Index: 1653056 (Python Code)

Max Activating Token Index: 849

Text #4

Max Range: 1.7294. Min Range: -1.7294

Max Act: 1.6183. Min Act: -0.0001

Data Index: 1496041 (Python Code)

Max Activating Token Index: 177

Text #5

Max Range: 1.7294. Min Range: -1.7294

Max Act: 1.4730. Min Act: -0.0001

Data Index: 1439528 (Python Code)

Max Activating Token Index: 448

Text #6

Max Range: 1.7294. Min Range: -1.7294

Max Act: 1.3832. Min Act: -0.0001

Data Index: 1562060 (Python Code)

Max Activating Token Index: 304

Text #7

Max Range: 1.7294. Min Range: -1.7294

Max Act: 1.2941. Min Act: -0.0001

Data Index: 1407399 (Python Code)

Max Activating Token Index: 336

Text #8

Max Range: 1.7294. Min Range: -1.7294

Max Act: 1.3184. Min Act: -0.0000

Data Index: 1118976 (C4 (Web Text))

Max Activating Token Index: 280

Text #9

Max Range: 1.7294. Min Range: -1.7294

Max Act: 1.3093. Min Act: -0.0000

Data Index: 812272 (C4 (Web Text))

Max Activating Token Index: 379

Text #10

Max Range: 1.7294. Min Range: -1.7294

Max Act: 1.3437. Min Act: -0.0001

Data Index: 1624950 (Python Code)

Max Activating Token Index: 427

Text #11

Max Range: 1.7294. Min Range: -1.7294

Max Act: 1.2743. Min Act: -0.0000

Data Index: 455031 (C4 (Web Text))

Max Activating Token Index: 858

Text #12

Max Range: 1.7294. Min Range: -1.7294

Max Act: 1.2754. Min Act: -0.0001

Data Index: 1505289 (Python Code)

Max Activating Token Index: 110

Text #13

Max Range: 1.7294. Min Range: -1.7294

Max Act: 1.2640. Min Act: -0.0001

Data Index: 700273 (C4 (Web Text))

Max Activating Token Index: 118

Text #14

Max Range: 1.7294. Min Range: -1.7294

Max Act: 1.4681. Min Act: -0.0001

Data Index: 1423152 (Python Code)

Max Activating Token Index: 330

Text #15

Max Range: 1.7294. Min Range: -1.7294

Max Act: 1.2200. Min Act: -0.0000

Data Index: 131743 (C4 (Web Text))

Max Activating Token Index: 975

Text #16

Max Range: 1.7294. Min Range: -1.7294

Max Act: 1.2531. Min Act: -0.0001

Data Index: 1407585 (Python Code)

Max Activating Token Index: 481

Text #17

Max Range: 1.7294. Min Range: -1.7294

Max Act: 1.2601. Min Act: -0.0000

Data Index: 979323 (C4 (Web Text))

Max Activating Token Index: 529

Text #18

Max Range: 1.7294. Min Range: -1.7294

Max Act: 1.1193. Min Act: -0.0001

Data Index: 1618262 (Python Code)

Max Activating Token Index: 674

Text #19

Max Range: 1.7294. Min Range: -1.7294

Max Act: 1.2339. Min Act: -0.0001

Data Index: 1284134 (C4 (Web Text))

Max Activating Token Index: 397